© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41798
    Prev
    Next
    INDEX
    Explanations

    rhythm, neutrality, solubility, immobilization, conservation, stretch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alink
    -0.08
    stek
    -0.08
    西æŀĹ
    -0.07
    缨
    -0.07
    è¡¥çŁŃ
    -0.07
    hani
    -0.07
    æ²ŁéĢļ交æµģ
    -0.07
    使çĶ¨å¯¿åij½éķ¿
    -0.06
    ç¨įç¨į
    -0.06
    çĴĭ
    -0.06
    POSITIVE LOGITS
    åħ¨éĿł
    0.08
     successfully
    0.08
     vs
    0.08
    å¦ĤåĪĿ
    0.07
    vs
    0.07
    ukes
    0.07
     ìľłì§Ģ
    0.07
    azor
    0.07
    大ä¸ļ
    0.07
    èĩ³ä¸Ĭ
    0.07
    Activations Density 0.145%

    No Known Activations